KemptenCity - Semantic Segmentation of Urban Areas for Simulation
- Autonomous driving and traffic flow simulation requires a realistic and accurate representation of the environment. Therefore, this research focuses on the semantic segmentation of aerial images for simulation purposes. Initially, a dataset was created based on true orthophotos from 2019 and Kempten’s street cadaster, with true orthophotos being fully rectified aerial images. The chosen classes were oriented towards the subsequent conversion and usage in simulation. The proposed labeling workflow used cadaster data and demonstrated significant time efficiency compared to state-of-the-art datasets. Subsequently, a neural network was implemented that was trained and tested on the dataset. In addition, the network was also trained only on the lane markings to compare the network’s performance. Both cases demonstrated excellent segmentation results. The generalizability was then tested on true orthophotos from 2021. The results indicated a solid generalizability, but still needs to be improved. Finally, the aerial information wasAutonomous driving and traffic flow simulation requires a realistic and accurate representation of the environment. Therefore, this research focuses on the semantic segmentation of aerial images for simulation purposes. Initially, a dataset was created based on true orthophotos from 2019 and Kempten’s street cadaster, with true orthophotos being fully rectified aerial images. The chosen classes were oriented towards the subsequent conversion and usage in simulation. The proposed labeling workflow used cadaster data and demonstrated significant time efficiency compared to state-of-the-art datasets. Subsequently, a neural network was implemented that was trained and tested on the dataset. In addition, the network was also trained only on the lane markings to compare the network’s performance. Both cases demonstrated excellent segmentation results. The generalizability was then tested on true orthophotos from 2021. The results indicated a solid generalizability, but still needs to be improved. Finally, the aerial information was converted into a 3D environment, that can be used in simulations. Our results confirm the usage of aerial imagery and street cadaster data as a basis for the simulations.…
Author: | Peter Buckel, Stefan-Alexander SchneiderORCiDGND, Jürgen StübnerORCiD, Florian Frank |
---|---|
URL / DOI: | https://isprs-annals.copernicus.org/articles/X-4-W5-2024/71/2024/ |
DOI: | https://doi.org/10.5194/isprs-annals-X-4-W5-2024-71-2024 |
Identifier: | 2194-9042 OPAC HS OPAC extern |
Identifier: | 2194-9050 OPAC HS OPAC extern |
Parent Title (English): | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Publisher: | Copernicus Publications |
Place of publication: | Katlenburg-Lindau |
Document Type: | conference proceeding (article) |
Conference: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume X-4/W5-2024 19th 3D GeoInfo Conference 2024, 1–3 July 2024, Vigo, Spain |
Language: | English |
Date of Publication (online): | 2024/06/27 |
Year of first Publication: | 2024 |
Tag: | Deep Learning; Digital Twin; Geoinformation Data; Remote Sensing; Simulation |
Volume: | 2024 |
Issue: | X-4/WS-2024 |
Number of pages: | 8 Seiten |
First Page: | 71 |
Last Page: | 78 |
Institutes: | Fakultät Elektrotechnik |
Dewey Decimal Classification: | 5 Naturwissenschaften und Mathematik / 55 Geowissenschaften, Geologie |
Open Access: | open_access |
Research focus: | FSP2: Mobilität |
Publication Lists: | Schneider, Stefan-Alexander |
Buckel, Peter | |
Stübner, Jürgen | |
Publication reviewed: | begutachtet |
Licence (German): | ![]() |
Release Date: | 2024/07/08 |